A deep learning framework identifies dimensional representations of Alzheimer's Disease from brain structure.
Zhijian YangIlya M NasrallahHaochang ShouJunhao WenJimit DoshiMohamad HabesGuray ErusAhmed AbdulkadirSusan M ResnickMarilyn S AlbertPaul MaruffJurgen FrippJohn C MorrisDavid A WolkChristos Davatzikosnull nullnull nullnull nullPublished in: Nature communications (2021)
Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a semi-supervised deep-clustering method, which examines neuroanatomical heterogeneity contrasted against normal brain structure, to identify disease subtypes through neuroimaging signatures. When applied to regional volumes derived from T1-weighted MRI (two studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified four patterns or axes of neurodegeneration. Applying this framework to longitudinal data revealed two distinct progression pathways. Measures of expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered complementary performance to amyloid/tau in predicting clinical progression. These deep-learning derived biomarkers offer potential for precision diagnostics and targeted clinical trial recruitment.
Keyphrases
- single cell
- deep learning
- cognitive impairment
- resting state
- machine learning
- white matter
- poor prognosis
- clinical trial
- contrast enhanced
- rna seq
- mild cognitive impairment
- functional connectivity
- genome wide
- cognitive decline
- computed tomography
- cerebral ischemia
- magnetic resonance
- artificial intelligence
- magnetic resonance imaging
- electronic health record
- big data
- randomized controlled trial
- multiple sclerosis
- cerebrospinal fluid
- long non coding rna
- network analysis
- double blind
- open label
- subarachnoid hemorrhage
- blood brain barrier
- climate change
- dual energy